mlsanityData to 7 Oct 2026

Analyzing Hate Speech Data along Racial, Gender and Intersectional Axes

arXiv 2205.06621 ↗First posted 13 May 2022cs.CL cs.AI cs.LGcited by 7

Not on the map. Why?

Abstract (arXiv)

To tackle the rising phenomenon of hate speech, efforts have been made towards data curation and analysis. When it comes to analysis of bias, previous work has focused predominantly on race. In our work, we further investigate bias in hate speech datasets along racial, gender and intersectional axes. We identify strong bias against African American English (AAE), masculine and AAE+Masculine tweets, which are annotated as disproportionately more hateful and offensive than from other demographics. We provide evidence that BERT-based models propagate this bias and show that balancing the training data for these protected attributes can lead to fairer models with regards to gender, but not race.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 15 of its 37 references that are in the map. First posted on arXiv 13 May 2022.

Builds on

15 of 37 references.

References · 15

  1. 2018Model Cards for Model Reportingcited by 1,068
  2. 2017Automated Hate Speech Detection and the Problem of Offensive Languagecited by 724
  3. 2018Gender Bias in Coreference Resolutioncited by 438
  4. 2020HateXplain: A Benchmark Dataset for Explainable Hate Speech Detectioncited by 403
  5. 2019Social Bias Frames: Reasoning about Social and Power Implications of Languagecited by 377
  6. 2018Large Scale Crowdsourcing and Characterization of Twitter Abusive Behaviorcited by 265
  7. 2019Racial Bias in Hate Speech and Abusive Language Detection Datasetscited by 208
  8. 2016Demographic Dialectal Variation in Social Media: A Case Study of African-American Englishcited by 194
  9. 2021Challenges in Automated Debiasing for Toxic Language Detectioncited by 95
  10. 2020Demoting Racial Bias in Hate Speech Detectioncited by 62
  11. 2020Investigating African-American Vernacular English in Transformer-Based Text Generationcited by 52
  12. 2021Hate Towards the Political Opponent: A Twitter Corpus Study of the 2020 US Elections on the Basis of Offensive Speech and Stance Detectioncited by 45
3 more
  1. 2020Intersectional Bias in Hate Speech and Abusive Language Datasetscited by 22
  2. 2021Towards Equal Gender Representation in the Annotations of Toxic Language Detectioncited by 9
  3. 2021From Toxicity in Online Comments to Incivility in American News: Proceed with Cautioncited by 8

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 1; 2025: 3.

7 papers.

  1. 2023Measuring Intersectional Biases in Historical Documentscited by 4
  2. 2025Characterizing Selective Refusal Bias in Large Language Modelscited by 4
  3. 2023Sociocultural knowledge is needed for selection of shots in hate speech detection taskscited by 1
  4. 2025Analysis of LLM as a grammatical feature tagger for African American Englishcited by 1
  5. 2025Evaluating LLMs for Demographic-Targeted Social Bias Detection: A Comprehensive Benchmark Studycited by 1
  6. 2023On the Challenges of Building Datasets for Hate Speech Detectioncited by 0
  7. 2024Disentangling Hate Across Target Identitiescited by 0